1
|
Machado MAD, Moraes TF, Anjos BHL, Alencar NRG, Chang TMC, Santana BCRF, Menezes VO, Vieira LO, Brandão SCS, Salvino MA, Netto EM. Association between increased Subcutaneous Adipose Tissue Radiodensity and cancer mortality: Automated computation, comparison of cancer types, gender, and scanner bias. Appl Radiat Isot 2024; 205:111181. [PMID: 38244325 DOI: 10.1016/j.apradiso.2024.111181] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/25/2023] [Revised: 12/17/2023] [Accepted: 01/04/2024] [Indexed: 01/22/2024]
Abstract
PURPOSE Body composition analysis using computed tomography (CT) is proposed as a predictor of cancer mortality. An association between subcutaneous adipose tissue radiodensity (SATr) and cancer-specific mortality was established, while gender effects and equipment bias were estimated. METHODS 7,475 CT studies were selected from 17 cohorts containing CT images of untreated cancer patients who underwent follow-up for a period of 2.1-118.8 months. SATr measures were collected from published data (n = 6,718) or calculated according to CT images using a deep-learning network (n = 757). The association between SATr and mortality was ascertained for each cohort and gender using the p-value from either logistic regression or ROC analysis. The Kruskal-Wallis test was used to analyze differences between gender distributions, and automatic segmentation was evaluated using the Dice score and five-point Likert quality scale. Gender effect, scanner bias and changes in the Hounsfield unit (HU) to detect hazards were also estimated. RESULTS Higher SATr was associated with mortality in eight cancer types (p < 0.05). Automatic segmentation produced a score of 0.949 while the quality scale measurement was good to excellent. The extent of gender effect was 5.2 HU while the scanner bias was 10.3 HU. The minimum proposed HU change to detect a patient at risk of death was between 5.6 and 8.3 HU. CONCLUSIONS CT imaging provides valuable assessments of body composition as part of the staging process for several cancer types, saving both time and cost. Gender specific scales and scanner bias adjustments should be carried out to successfully implement SATr measures in clinical practice.
Collapse
Affiliation(s)
- Marcos A D Machado
- Department of Radiology, Complexo Hospitalar Universitário Prof. Edgard Santos/ Ebserh, Universidade Federal da Bahia, Salvador, Bahia, Zip code: 40.110-040, Brazil; Nuclear Medicine Department, São Rafael Hospital/ Rededor, Salvador, Bahia, Zip code: 41.253-190, Brazil; Nuclearis Corporation, Recife, Pernambuco, Zip code: 50.030-200, Brazil.
| | - Thauan F Moraes
- Northeast Center for Strategic Technologies, Universidade Federal de Pernambuco, Recife, Pernambuco, Zip code: 50.740-545, Brazil
| | - Bruno H L Anjos
- Nuclearis Corporation, Recife, Pernambuco, Zip code: 50.030-200, Brazil
| | - Nadja R G Alencar
- Radiology and Nuclear Medicine Department, Hospital das Clínicas, Federal University of Pernambuco, Recife, Pernambuco, Zip code: 50.670-901, Brazil
| | - Tien-Man C Chang
- Nuclear Medicine Department, Instituto de Medicina Integrada Fernandes Figueira, Recife, Pernambuco, Zip code: 50.070-902, Brazil
| | - Bruno C R F Santana
- Nuclear Medicine Department, São Rafael Hospital/ Rededor, Salvador, Bahia, Zip code: 41.253-190, Brazil
| | - Vinicius O Menezes
- Nuclear Medicine Department, São Rafael Hospital/ Rededor, Salvador, Bahia, Zip code: 41.253-190, Brazil; Nuclearis Corporation, Recife, Pernambuco, Zip code: 50.030-200, Brazil; Radiology and Nuclear Medicine Department, Hospital das Clínicas, Federal University of Pernambuco/ Ebserh, Recife, Pernambuco, Zip code: 50.670-901, Brazil
| | - Lucas O Vieira
- Nuclear Medicine Department, São Rafael Hospital/ Rededor, Salvador, Bahia, Zip code: 41.253-190, Brazil
| | - Simone C S Brandão
- Radiology and Nuclear Medicine Department, Hospital das Clínicas, Federal University of Pernambuco, Recife, Pernambuco, Zip code: 50.670-901, Brazil
| | - Marco A Salvino
- Complexo Hospitalar Universitário Prof. Edgard Santos/ Ebserh, Universidade Federal da Bahia, Salvador, Bahia, Zip code: 40.110-040, Brazil; Hemathology Department, São Rafael Hospital, Salvador, Bahia, Zip code: 41.253-190, Brazil
| | - Eduardo M Netto
- Infectious Disease Research Laboratory, Complexo Hospitalar Universitário Prof. Edgard Santos/ Ebserh, Universidade Federal da Bahia, Salvador, Bahia, Zip code: 40.110-040, Brazil
| |
Collapse
|
2
|
Machado MAD, Silva RRE, Namias M, Lessa AS, Neves MCLC, Silva CTA, Oliveira DM, Reina TR, Lira AAB, Almeida LM, Zanchettin C, Netto EM. Multi-center Integrating Radiomics, Structured Reports, and Machine Learning Algorithms for Assisted Classification of COVID-19 in Lung Computed Tomography. J Med Biol Eng 2023; 43:156-162. [PMID: 37077697 PMCID: PMC9990550 DOI: 10.1007/s40846-023-00781-4] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/07/2022] [Accepted: 02/16/2023] [Indexed: 04/21/2023]
Abstract
Purpose To evaluate the classification performance of structured report features, radiomics, and machine learning (ML) models to differentiate between Coronavirus Disease 2019 (COVID-19) and other types of pneumonia using chest computed tomography (CT) scans. Methods Sixty-four COVID-19 subjects and 64 subjects with non-COVID-19 pneumonia were selected. The data was split into two independent cohorts: one for the structured report, radiomic feature selection and model building (n = 73), and another for model validation (n = 55). Physicians performed readings with and without machine learning support. The model's sensitivity and specificity were calculated, and inter-rater reliability was assessed using Cohen's Kappa agreement coefficient. Results Physicians performed with mean sensitivity and specificity of 83.4 and 64.3%, respectively. When assisted with machine learning, the mean sensitivity and specificity increased to 87.1 and 91.1%, respectively. In addition, machine learning improved the inter-rater reliability from moderate to substantial. Conclusion Integrating structured reports and radiomics promises assisted classification of COVID-19 in CT chest scans.
Collapse
Affiliation(s)
- Marcos A. D. Machado
- Department of Radiology, Complexo Hospitalar Universitário Prof. Edgard Santos/ Ebserh, Universidade Federal da Bahia, Salvador, Bahia 40110-040 Brazil
- Radtec Serviços em Física Médica, Salvador, Bahia 40060-330 Brazil
| | - Ronnyldo R. E. Silva
- Radtec Serviços em Física Médica, Salvador, Bahia 40060-330 Brazil
- Department of Systems and Computing, Universidade Federal de Campina Grande, Campina Grande, Paraíba 58429-900 Brazil
| | - Mauro Namias
- Department of Medical Physics, Nuclear Diagnostic Center Foundation, C1417CVE Buenos Aires, Argentina
| | - Andreia S. Lessa
- Department of Radiology, Hospital Universitário Gaffrée e Guinle, Universidade do Rio de Janeiro (UNIRIO), Rio de Janeiro, 20270-004 Brazil
| | - Margarida C. L. C. Neves
- Department of Pneumology, Complexo Hospitalar Universitário Prof. Edgard Santos/ Ebserh, Universidade Federal da Bahia, Salvador, Bahia 40110-040 Brazil
| | - Carolina T. A. Silva
- Department of Radiology, Complexo Hospitalar Universitário Prof. Edgard Santos/ Ebserh, Universidade Federal da Bahia, Salvador, Bahia 40110-040 Brazil
| | - Danillo M. Oliveira
- Department of Radiology, Hospital Universitário Alcides Carneiro/ Ebserh, Universidade Federal de Campina Grande, Campina Grande, Paraíba 58400-398 Brazil
- Northeast Regional Nuclear Science Centre (CRCN-NE), Recife, Pernambuco 50840-545 Brazil
- Nuclear Energy Department, Universidade Federal de Pernambuco, Recife, Pernambuco 50740-540 Brazil
| | - Thamiris R. Reina
- Department of Radiology, Hospital Universitário da Universidade Federal de Juiz de Fora/ Ebserh, Universidade Federal de Juiz de Fora, Juiz de Fora, Minas Gerais 36038-330 Brazil
| | - Arquimedes A. B. Lira
- Department of Radiology, Hospital Universitário Alcides Carneiro/ Ebserh, Universidade Federal de Campina Grande, Campina Grande, Paraíba 58400-398 Brazil
| | - Leandro M. Almeida
- Centro de Informática, Universidade Federal de Pernambuco, Recife, Pernambuco 50720-001 Brazil
| | - Cleber Zanchettin
- Centro de Informática, Universidade Federal de Pernambuco, Recife, Pernambuco 50720-001 Brazil
- Department of Chemical and Biological Engineering, Northwestern University, Evanston, IL 60208 USA
| | - Eduardo M. Netto
- Infectious Disease Research Laboratory, Complexo Hospitalar Universitário Prof. Edgard Santos/ Ebserh, Universidade Federal da Bahia, Salvador, Bahia 40110-040 Brazil
| |
Collapse
|
3
|
Machado MAD, Menezes VO, Namías M, Vieira NS, Queiroz CC, Matheoud R, Alessio AM, Oliveira ML. Protocols for Harmonized Quantification and Noise Reduction in Low-Dose Oncologic 18F-FDG PET/CT Imaging. J Nucl Med Technol 2018; 47:47-54. [PMID: 30076252 DOI: 10.2967/jnmt.118.213405] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2018] [Accepted: 07/26/2018] [Indexed: 11/16/2022] Open
Affiliation(s)
- Marcos A D Machado
- Nuclear Medicine Department, São Rafael Hospital, Salvador, Brazil
- Hospital das Clínicas da Universidade Federal de Bahia/Ebserh, Salvador, Brazil
| | - Vinícius O Menezes
- Nuclear Medicine Department, São Rafael Hospital, Salvador, Brazil
- Hospital das Clínicas da Universidade Federal de Pernambuco/Ebserh, Recife, Brazil
| | - Mauro Namías
- Fundación Centro Diagnóstico Nuclear, Buenos Aires, Argentina
| | - Naiara S Vieira
- Nuclear Medicine Department, São Rafael Hospital, Salvador, Brazil
| | - Cleiton C Queiroz
- Nuclear Medicine Department, São Rafael Hospital, Salvador, Brazil
- Hospital Universitario Professor Alberto Antunes/Ebserh, Maceió, Brazil
| | - Roberta Matheoud
- Department of Medical Physics, Azienda Ospedaliera Maggiore della Carità, Novara, Italy
| | - Adam M Alessio
- Department of Radiology, University of Washington, Seattle, Washington; and
| | - Mércia L Oliveira
- Centro Regional de Ciências Nucleares (CRCN-NE)/CNEN, Recife, Brazil
| |
Collapse
|
4
|
|
5
|
Menezes VO, Machado MAD, Queiroz CC, Souza SO, d'Errico F, Namías M, Larocca TF, Soares MBP. Optimization of oncological ¹⁸F-FDG PET/CT imaging based on a multiparameter analysis. Med Phys 2016; 43:930-8. [PMID: 26843253 DOI: 10.1118/1.4940354] [Citation(s) in RCA: 9] [Impact Index Per Article: 1.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/07/2022] Open
Abstract
PURPOSE This paper describes a method to achieve consistent clinical image quality in (18)F-FDG scans accounting for patient habitus, dose regimen, image acquisition, and processing techniques. METHODS Oncological PET/CT scan data for 58 subjects were evaluated retrospectively to derive analytical curves that predict image quality. Patient noise equivalent count rate and coefficient of variation (CV) were used as metrics in their analysis. Optimized acquisition protocols were identified and prospectively applied to 179 subjects. RESULTS The adoption of different schemes for three body mass ranges (<60 kg, 60-90 kg, >90 kg) allows improved image quality with both point spread function and ordered-subsets expectation maximization-3D reconstruction methods. The application of this methodology showed that CV improved significantly (p < 0.0001) in clinical practice. CONCLUSIONS Consistent oncological PET/CT image quality on a high-performance scanner was achieved from an analysis of the relations existing between dose regimen, patient habitus, acquisition, and processing techniques. The proposed methodology may be used by PET/CT centers to develop protocols to standardize PET/CT imaging procedures and achieve better patient management and cost-effective operations.
Collapse
Affiliation(s)
- Vinicius O Menezes
- Nuclear Medicine Department, São Rafael Hospital, Salvador 41720-375, Brazil and Nuclear Medicine Department, Hospital das Clínicas da Universidade Federal de Pernambuco/Ebserh, Recife 50670-901, Brazil
| | - Marcos A D Machado
- Nuclear Medicine Department, São Rafael Hospital, Salvador 41720-375, Brazil and Nuclear Medicine Department, Hospital das Clínicas da Universidade Federal de Bahia/Ebserh, Salvador 40110-060, Brazil
| | - Cleiton C Queiroz
- Nuclear Medicine Department, São Rafael Hospital, Salvador 41720-375, Brazil and Nuclear Medicine Department, Hospital Universitário Professor Alberto Antunes/Ebserh, Maceió 57072-900, Brazil
| | - Susana O Souza
- Department of Physics, Universidade Federal de Sergipe, São Cristóvão 49100-000, Brazil
| | - Francesco d'Errico
- Department of Diagnostic Radiology, Yale University School of Medicine, New Haven, Connecticut 06520 and School of Engineering, University of Pisa, Pisa 56126, Italy
| | - Mauro Namías
- Fundación Centro Diagnóstico Nuclear, Buenos Aires C1417CVE, Argentina
| | - Ticiana F Larocca
- Centro de Biotecnologia e Terapia Celular, São Rafael Hospital, Salvador 41253-190, Brazil
| | - Milena B P Soares
- Centro de Biotecnologia e Terapia Celular, São Rafael Hospital, Salvador 41253-190, Brazil and Fundação Oswaldo Cruz, Centro de Pesq. Gonçalo Moniz, Salvador 40296-710, Brazil
| |
Collapse
|